Conference proceeding
Image Enhancement for Extremely Low Light Conditions
2014 11TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), pp 307-312
01 Jan 2014
Abstract
In this paper, a novel methodology is proposed for contrast enhancement and noise reduction in very noisy data with low dynamic range on images captured by surveillance camera under extremely low light condition. For the initial noise reduction, a motion adaptive temporal filtering based on the Kalman filter is employed. Then, the denoised image is first inverted and subsequently dehazed as a tone mapping to enhance the visibility based on the observation that the inverted low light image presents quite similar characteristics to hazy image. Finally, the remaining noise is removed using the Non-local means (NLM) denoising step. The overall approach essentially transforms very dark images progressively into more visible form and effectively reduces the high intensity noise generated by the tone mapping process. From the experimental results, effectiveness of the proposed method is validated by comparing with the most recent and leading conventional method.
Metrics
Details
- Title
- Image Enhancement for Extremely Low Light Conditions
- Creators
- Dubok Park - Korea UniversityMinjae Kim - Korea UniversityBonhwa Ku - Korea UniversitySangmin Yoon - Kookmin UniversityDavid K. Han - Office of Naval Research
- Publication Details
- 2014 11TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), pp 307-312
- Publisher
- IEEE
- Number of pages
- 6
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000365607900052
- Scopus ID
- 2-s2.0-84909964311
- Other Identifier
- 991021931087404721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Engineering, Electrical & Electronic